News for hackers. Stuff that matters.
Re:We Must Pace the Frontier by estearum on Saturday September 12, 2026 @04:27PM (#49676841)
The entire premise of alignment detection is pretty much nonsense at this point. The models reliably detect when they're being evaluated and will modify their behavior and deliberately obfuscate their "chain of thought" (which is correlated, at best, with their actual "internal deliberations").

There are no comments on this comment yet.